DP10939 Attention and Saliency on the Internet: Evidence from an Online Recommendation System
Using high-frequency transaction-level data from an online retail store, we examine whether consumer choices on the internet are consistent with models of limited attention. We test whether consumers are more likely to buy products that receive a saliency shock when they are recommended by new products. To identify the saliency effect, we rely on i) the timing of new product arrivals, ii) the fact that new products are per se highly salient upon arrival, drawing more attention and iii) regional variation in the composition of recommendation sets. We find a sharp and robust 6% increase in the aggregate sales of existing products after they are recommended by a new product. To structurally disentangle the effect of saliency on a consumer?s consideration and choice decision, we use data on individual transactions to estimate a probabilistic choice set model. We find that the saliency effect is driven largely by an expansion of consumers? consideration sets.